# Understanding Data Augmentation from a Robustness Perspective

arXiv: https://arxiv.org/abs/2311.12800 · HTML: https://mlsanity.com/paper/2311.12800/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 7 Sep 2023.

## Builds on (most cited first, 23 of 23)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation](https://mlsanity.com/paper/2103.10158/) (2021)
- [Understanding The Robustness in Vision Transformers](https://mlsanity.com/paper/2204.12451/) (2022)
- [PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures](https://mlsanity.com/paper/2112.05135/) (2021)
- [A Kernel Theory of Modern Data Augmentation](https://mlsanity.com/paper/1803.06084/) (2018)
- [On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness](https://mlsanity.com/paper/2102.11273/) (2021)
- [Posterior calibration and exploratory analysis for natural language processing models](https://mlsanity.com/paper/1508.05154/) (2015)
- [Discovering and Explaining the Representation Bottleneck of DNNs](https://mlsanity.com/paper/2111.06236/) (2021)
- [Interpreting and Boosting Dropout from a Game-Theoretic View](https://mlsanity.com/paper/2009.11729/) (2020)
- [Sample Efficiency of Data Augmentation Consistency Regularization](https://mlsanity.com/paper/2202.12230/) (2022)
- [Enhance the Visual Representation via Discrete Adversarial Training](https://mlsanity.com/paper/2209.07735/) (2022)
- [A Unified Game-Theoretic Interpretation of Adversarial Robustness](https://mlsanity.com/paper/2111.03536/) (2021)
- [A Game-Theoretic Taxonomy of Visual Concepts in DNNs](https://mlsanity.com/paper/2106.10938/) (2021)

## Built on by (most cited first, 3 of 3)

- [SETA: Semantic-Aware Token Augmentation for Domain Generalization](https://mlsanity.com/paper/2403.11792/) (2024)
- [A Flat Minima Perspective on Understanding Augmentations and Model Robustness](https://mlsanity.com/paper/2505.24592/) (2025)
- [Fair Context Learning for Evidence-Balanced Test-Time Adaptation in Vision-Language Models](https://mlsanity.com/paper/2602.07027/) (2026)

## Abstract (arXiv)

In the realm of visual recognition, data augmentation stands out as a pivotal technique to amplify model robustness. Yet, a considerable number of existing methodologies lean heavily on heuristic foundations, rendering their intrinsic mechanisms ambiguous. This manuscript takes both a theoretical and empirical approach to understanding the phenomenon. Theoretically, we frame the discourse around data augmentation within game theory's constructs. Venturing deeper, our empirical evaluations dissect the intricate mechanisms of emblematic data augmentation strategies, illuminating that these techniques primarily stimulate mid- and high-order game interactions. Beyond the foundational exploration, our experiments span multiple datasets and diverse augmentation techniques, underscoring the universal applicability of our findings. Recognizing the vast array of robustness metrics with intricate correlations, we unveil a streamlined proxy. This proxy not only simplifies robustness assessment but also offers invaluable insights, shedding light on the inherent dynamics of model game interactions and their relation to overarching system robustness. These insights provide a novel lens through which we can re-evaluate model safety and robustness in visual recognition tasks.